{"id":"https://openalex.org/W4392788562","doi":"https://doi.org/10.1155/2024/6671359","title":"Parsing of Research Documents into XML Using Formal Grammars","display_name":"Parsing of Research Documents into XML Using Formal Grammars","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392788562","doi":"https://doi.org/10.1155/2024/6671359"},"language":"en","primary_location":{"id":"doi:10.1155/2024/6671359","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2024/6671359","pdf_url":"https://downloads.hindawi.com/journals/acisc/2024/6671359.pdf","source":{"id":"https://openalex.org/S30680879","display_name":"Applied Computational Intelligence and Soft Computing","issn_l":"1687-9724","issn":["1687-9724","1687-9732"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Computational Intelligence and Soft Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://downloads.hindawi.com/journals/acisc/2024/6671359.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055995590","display_name":"Opeoluwa Iwashokun","orcid":"https://orcid.org/0000-0002-6220-248X"},"institutions":[{"id":"https://openalex.org/I24027795","display_name":"University of Johannesburg","ror":"https://ror.org/04z6c2n17","country_code":"ZA","type":"education","lineage":["https://openalex.org/I24027795"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Opeoluwa Iwashokun","raw_affiliation_strings":["Department of Applied Information Systems, College of Business and Economics, University of Johannesburg, Johannesburg"],"raw_orcid":"https://orcid.org/0000-0002-6220-248X","affiliations":[{"raw_affiliation_string":"Department of Applied Information Systems, College of Business and Economics, University of Johannesburg, Johannesburg","institution_ids":["https://openalex.org/I24027795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004107129","display_name":"Abejide Ade-Ibijola","orcid":"https://orcid.org/0000-0001-9507-0455"},"institutions":[{"id":"https://openalex.org/I24027795","display_name":"University of Johannesburg","ror":"https://ror.org/04z6c2n17","country_code":"ZA","type":"education","lineage":["https://openalex.org/I24027795"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Abejide Ade-Ibijola","raw_affiliation_strings":["Research Group on Data, Artificial Intelligence, and Innovations for Digital Transformation, Johannesburg Business School, University of Johannesburg, Johannesburg"],"raw_orcid":"https://orcid.org/0000-0001-9507-0455","affiliations":[{"raw_affiliation_string":"Research Group on Data, Artificial Intelligence, and Innovations for Digital Transformation, Johannesburg Business School, University of Johannesburg, Johannesburg","institution_ids":["https://openalex.org/I24027795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055995590"],"corresponding_institution_ids":["https://openalex.org/I24027795"],"apc_list":{"value":900,"currency":"USD","value_usd":900},"apc_paid":{"value":900,"currency":"USD","value_usd":900},"fwci":1.9449,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87262242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"2024","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.926423192024231},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5745682120323181},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5626477599143982},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.512952983379364},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5086451768875122},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5043579339981079},{"id":"https://openalex.org/keywords/simple-api-for-xml","display_name":"Simple API for XML","score":0.41429242491722107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4114440977573395},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.4035188853740692},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3866112530231476},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27310481667518616},{"id":"https://openalex.org/keywords/xml-signature","display_name":"XML Signature","score":0.17556223273277283}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.926423192024231},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5745682120323181},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5626477599143982},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.512952983379364},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5086451768875122},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5043579339981079},{"id":"https://openalex.org/C8595896","wikidata":"https://www.wikidata.org/wiki/Q577094","display_name":"Simple API for XML","level":5,"score":0.41429242491722107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4114440977573395},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.4035188853740692},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3866112530231476},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27310481667518616},{"id":"https://openalex.org/C34330436","wikidata":"https://www.wikidata.org/wiki/Q979532","display_name":"XML Signature","level":4,"score":0.17556223273277283}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1155/2024/6671359","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2024/6671359","pdf_url":"https://downloads.hindawi.com/journals/acisc/2024/6671359.pdf","source":{"id":"https://openalex.org/S30680879","display_name":"Applied Computational Intelligence and Soft Computing","issn_l":"1687-9724","issn":["1687-9724","1687-9732"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Computational Intelligence and Soft Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:571daae31c404ae2ae3de545c3cc7219","is_oa":true,"landing_page_url":"https://doaj.org/article/571daae31c404ae2ae3de545c3cc7219","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Applied Computational Intelligence and Soft Computing, Vol 2024 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2024/6671359","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2024/6671359","pdf_url":"https://downloads.hindawi.com/journals/acisc/2024/6671359.pdf","source":{"id":"https://openalex.org/S30680879","display_name":"Applied Computational Intelligence and Soft Computing","issn_l":"1687-9724","issn":["1687-9724","1687-9732"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Computational Intelligence and Soft Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2150570522","display_name":null,"funder_award_id":"119041","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321038","display_name":"Fonds National de la Recherche Luxembourg","ror":"https://ror.org/039z13y21"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392788562.pdf"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W791527587","https://openalex.org/W1218692728","https://openalex.org/W1603719052","https://openalex.org/W1983284692","https://openalex.org/W2038564898","https://openalex.org/W2061598441","https://openalex.org/W2109711517","https://openalex.org/W2116141134","https://openalex.org/W2125812480","https://openalex.org/W2146305921","https://openalex.org/W2523785361","https://openalex.org/W2529247374","https://openalex.org/W2530002960","https://openalex.org/W2768926640","https://openalex.org/W2772007068","https://openalex.org/W2885051956","https://openalex.org/W2905388948","https://openalex.org/W2911656629","https://openalex.org/W2914408744","https://openalex.org/W2943174194","https://openalex.org/W2955108721","https://openalex.org/W2963899396","https://openalex.org/W2970819616","https://openalex.org/W2974498669","https://openalex.org/W2991344441","https://openalex.org/W3003261556","https://openalex.org/W3007287533","https://openalex.org/W3013442610","https://openalex.org/W3028968453","https://openalex.org/W3047350056","https://openalex.org/W3104637907","https://openalex.org/W3144691914","https://openalex.org/W3198609383","https://openalex.org/W3202285719","https://openalex.org/W3217771537","https://openalex.org/W4220830656","https://openalex.org/W4221047533","https://openalex.org/W4285125113","https://openalex.org/W4285791949","https://openalex.org/W4289865841","https://openalex.org/W4291158197","https://openalex.org/W4293690005","https://openalex.org/W4308555882","https://openalex.org/W4308590518","https://openalex.org/W4313262066","https://openalex.org/W4318186079","https://openalex.org/W4320014603","https://openalex.org/W4362717730","https://openalex.org/W6920550535","https://openalex.org/W6982521223"],"related_works":["https://openalex.org/W2366867683","https://openalex.org/W2118045671","https://openalex.org/W2347775463","https://openalex.org/W2058941326","https://openalex.org/W2024164996","https://openalex.org/W2149546672","https://openalex.org/W1972245780","https://openalex.org/W2112528798","https://openalex.org/W2353138694","https://openalex.org/W2011024487"],"abstract_inverted_index":{"Automatic":[0],"information":[1,116,181,197],"extraction":[2,110,182],"of":[3,17,25,57,70,79,111,117,142,151,171],"content":[4,33],"and":[5,32,74,114,132,155,161,187],"style":[6],"format":[7],"in":[8,183,195],"paged":[9],"documents":[10,61,93,150,186,190],"is":[11,34,174],"challenging.":[12],"It":[13],"requires":[14],"the":[15,18,88,109,118,193],"conversion":[16],"original":[19],"document":[20,30,47],"into":[21,62,94,121],"a":[22,66,80,85,139],"granular":[23],"level":[24],"details":[26],"for":[27,43,87,180],"which":[28],"every":[29],"section":[31],"identifiable.":[35],"This":[36],"functionality":[37],"or":[38],"tool":[39,86,107,137,160],"does":[40],"not":[41],"exist":[42],"any":[44],"academic":[45,188],"research":[46,59,149,189,194],"yet.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"present":[53],"an":[54],"automated":[55],"process":[56,173],"parsing":[58],"paper":[60],"XML":[63,99,122,125],"files":[64,100,127],"using":[65],"formal":[67,178],"method":[68],"approach":[69],"context\u2010free":[71],"grammars":[72],"(CFGs)":[73],"regular":[75],"expressions":[76],"(REGEXs)":[77],"definable":[78],"standard":[81],"template.":[82],"We":[83],"created":[84],"algorithms":[89],"to":[90,176],"parse":[91],"these":[92],"tree\u2010like":[95],"structures":[96],"organized":[97],"as":[98],"named":[101],"research_XML":[102],"(RX)":[103],"parser.":[104],"The":[105,135,159,169],"RX":[106,136],"performed":[108],"syntactic":[112],"structure":[113],"semantic":[115],"document\u2019s":[119],"contents":[120],"files.":[123],"These":[124],"output":[126],"are":[128,164],"lightweight,":[129],"analyzable,":[130],"query\u2010able,":[131],"web":[133],"interoperable.":[134],"has":[138],"success":[140],"rate":[141],"91%":[143],"when":[144],"evaluated":[145],"on":[146,166],"fifty":[147],"varying":[148],"160":[152],"average":[153],"pages":[154],"8,004":[156],"total":[157],"pages.":[158],"test":[162],"data":[163],"accessible":[165],"GitHub":[167],"repo.":[168],"novelty":[170],"our":[172],"specific":[175],"applying":[177],"techniques":[179],"structured":[184],"multipaged":[185],"thus":[191],"advancing":[192],"automatic":[196],"extraction.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
